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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or intention

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

    Following "want" or "wanna"

    np_acts-logits-general · gemini-2.0-flash

    avoid unwanted things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.54
     мәкал
    -0.51
    ernoo
    -0.42
    ("'"
    -0.41
    rinfo
    -0.40
    DockStyle
    -0.40
    msgSender
    -0.39
    IntoConstraints
    -0.39
    unknownFields
    -0.39
    osoba
    -0.39
    POSITIVE LOGITS
     unwanted
    0.75
     unwelcome
    0.65
     reluctant
    0.64
    不想
    0.61
     unpleasant
    0.58
     takut
    0.56
     unwilling
    0.55
     ناخ
    0.53
    avoid
    0.53
     undesirable
    0.53
    Act Density 0.240%

    No Known Activations