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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or conditionality regarding actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    746
    -0.14
    QualifiedName
    -0.13
    ìĨį
    -0.13
    okrat
    -0.13
    vk
    -0.13
    ivec
    -0.13
    .IsNullOr
    -0.12
    ıb
    -0.12
    ãģıãģª
    -0.12
    Activation
    -0.12
    POSITIVE LOGITS
     able
    0.80
     ability
    0.65
     Able
    0.60
    èĥ½å¤Ł
    0.57
     Ability
    0.53
    èĥ½
    0.50
     èĥ½
    0.49
    Ability
    0.46
     capable
    0.43
    ability
    0.41
    Act Density 0.320%

    No Known Activations