Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intentions, purposes, or designations related to actions or interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Infinitive verbs

    np_acts-logits-general · gemini-2.0-flash

    aid actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.56
     IndexPath
    -0.52
    viewDidLoad
    -0.52
    UseVisualStyle
    -0.52
    ArgsConstructor
    -0.50
    -0.49
    resave
    -0.49
     ProtoMessage
    -0.49
    Scroll
    -0.48
    think
    -0.48
    POSITIVE LOGITS
     facilitate
    0.91
     promote
    0.81
     enable
    0.79
     improve
    0.78
     aid
    0.76
     assist
    0.76
     prevent
    0.75
     encourage
    0.75
     help
    0.74
     enhance
    0.72
    Act Density 0.441%

    No Known Activations