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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating a preference or tendency towards a particular action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to willingness or tendency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UU
    -0.75
    Nation
    -0.68
    mel
    -0.67
    oufl
    -0.67
     Drama
    -0.67
     Semin
    -0.66
    ARDS
    -0.65
     Boom
    -0.65
    ARD
    -0.64
    recorded
    -0.64
    POSITIVE LOGITS
     inclined
    1.47
     inclination
    1.18
     guiActiveUn
    0.93
     tempted
    0.93
    ¿½
    0.85
    ĺħ
    0.84
     incl
    0.84
     suscept
    0.84
    lihood
    0.82
    userc
    0.81
    Act Density 0.007%

    No Known Activations