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

    Neuronpedia

    INDEX
    Explanations

    terms related to changes and variations in quantitative measures or parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.60
    casian
    -0.55
    joba
    -0.54
    éez
    -0.53
    cipl
    -0.52
    Introduce
    -0.52
    arks
    -0.52
    employed
    -0.51
     strtok
    -0.51
     addressing
    -0.50
    POSITIVE LOGITS
     grows
    0.72
    躇
    0.71
     zune
    0.67
     progresses
    0.66
     decays
    0.65
     evolves
    0.65
     progre
    0.65
     escalation
    0.64
     shrinking
    0.61
     escalating
    0.60
    Act Density 0.701%

    No Known Activations