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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating creation or achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.79
    AndEndTag
    -0.60
     HasFactory
    -0.54
     Chwiliwch
    -0.54
    PostInfinity
    -0.51
    ScopeManager
    -0.50
    ValueStyle
    -0.49
    !*\
    -0.48
     ब्रेकडाउन
    -0.47
    PerformLayout
    -0.47
    POSITIVE LOGITS
     noise
    0.48
     impact
    0.47
     headlines
    0.47
     schaffen
    0.46
    impact
    0.46
    made
    0.45
     made
    0.44
    noise
    0.44
     waves
    0.43
    Made
    0.42
    Act Density 0.115%

    No Known Activations